A Review of Ensemble Learning Algorithms Used in Remote Sensing Applications

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(17), P. 8654 - 8654

Published: Aug. 29, 2022

Machine learning algorithms are increasingly used in various remote sensing applications due to their ability identify nonlinear correlations. Ensemble have been included many practical improve prediction accuracy. We provide an overview of three widely ensemble techniques: bagging, boosting, and stacking. first the underlying principles present analysis current literature. summarize some typical algorithms, which include predicting crop yield, estimating forest structure parameters, mapping natural hazards, spatial downscaling climate parameters land surface temperature. Finally, we suggest future directions for using applications.

Language: Английский

---

A hybrid of ensemble machine learning models with RFE and Boruta wrapper-based algorithms for flash flood susceptibility assessment

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 122, P. 103401 - 103401

Published: July 14, 2023

Flash floods are among the world most destructive natural disasters, and developing optimum hybrid Machine Learning (ML) models for flash flood susceptibility (FFS) modeling remains a challenge. This study proposed novel intelligence algorithms based on of several ensemble ML (i.e., Bagged Flexible Discriminant Analysis (BAFDA), Extreme Gradient Boosting (XBG), Rotation Forest (ROF) Boosted Generalized Additive Model (BGAM)) wrapper-based factor optimization Recursive Feature Elimination (RFE) Boruta) to improve accuracy FFS mapping at Neka-Haraz watershed in Iran. In addition, Random Search (RS) method is meta-optimization developed hyper-parameters. considers 20 conditioning factors (CgFs) 380 non-flood locations create geospatial database. The performance each model was evaluated by area under receiver operating characteristic (ROC) curve (AUC) validation methods, such as efficiency. demonstrated good performance, with BGAM-Boruta achieving highest (AUC = 0.953, Efficiency 0.910), followed ROF-Boruta 0.952), ROF-RFE 0.951), BAFDA-Boruta 0.950), BGAM-RFE ROF 0.949), BGAM 0.948), BAFDA-RFE 0.943), XGB-Boruta BAFDA 0.939), XGB-RFE 0.938) XGB 0.911). model, regional coverage about 46% high very areas. Moreover, revealed that distance river, slope, rainfall, altitude, road CgFs significant this region.

Language: Английский

---

Physics-informed optimization for a data-driven approach in landslide susceptibility evaluation

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2024, Volume and Issue: 16(8), P. 3192 - 3205

Published: March 16, 2024

Landslide susceptibility mapping is an integral part of geological hazard analysis. Recently, the emphasis many studies has been on data-driven models, notably those derived from machine learning, owing to their aptitude for tackling complex non-linear problems. However, prevailing models often disregard qualitative research, leading limited interpretability and mistakes in extracting negative samples, i.e. inaccurate non-landslide samples. In this study, Scoops 3D (a three-dimensional slope stability analysis tool) was utilized conduct a assessment Yunyang section Three Gorges Reservoir area. The depth bedrock predicted utilizing Convolutional Neural Network (CNN), incorporating local boreholes building insights prior research. Random Forest (RF) algorithm subsequently used execute landslide proposed methodology demonstrated notable increase 29.25% evaluation metric, area under receiver operating characteristic curve (ROC-AUC), outperforming benchmark model. Furthermore, map generated by model superior interpretability. This result not only validates effectiveness amalgamating mathematical mechanistic such analyses, but it also carries substantial academic practical implications.

Language: Английский

---

BisDeNet: A New Lightweight Deep Learning-Based Framework for Efficient Landslide Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 3648 - 3663

Published: Jan. 1, 2024

Landslides are catastrophic geological events that can cause significant damage to properties and result in the loss of human lives. Deep learning technology applied optical remote sensing images enable effective landslide-prone area detection. However, conventional landslide detection (LD) models often employ complex structural designs ensure accuracy. The complexity hampers speed, rendering these inadequate for swift emergency monitoring landslides. To address problems, we propose a new lightweight deep learning-based framework, BisDeNet, efficient LD. improve efficiency proposed replaced context path original BiSeNet with DenseNet due its strong feature extraction ability, few required parameters, low model complexity. Two sites different representative developments were selected as study areas verify performance our BisDeNet. Additionally, introduced causative factors enhance sampling dataset. evaluate effectiveness approach, compared BisDeNet performances three other BiSeNet-based methods an advanced Transformer-based DeiT (Data-efficient Image Transformer). Our experimental results indicate F1 scores two 0.9006 0.8850, which 26.22% 1.86% higher than BiSeNet, respectively, but slightly lower model. Furthermore, requires fewest number parameters least memory out five models.

Language: Английский

---

Improving landslide susceptibility prediction through ensemble recursive feature elimination and meta-learning framework

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 12, 2025

Abstract Landslides pose significant threats to ecosystems, lives, and economies, particularly in the geologically fragile Sub-Himalayan region of West Bengal, India. This study enhances landslide susceptibility prediction by developing an ensemble framework integrating Recursive Feature Elimination (RFE) with meta-learning techniques. Seven advanced machine learning models- Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting (GB), Extreme (XGBoost), a Meta Classifier (MC) were applied using Remote Sensing GIS tools identify key landslide-conditioning factors classify zones. Model performance was assessed through metrics such as accuracy, precision, recall, F1 score, AUC ROC curve. Among models, achieved highest accuracy (0.956) (0.987), demonstrating superior predictive ability. XGBoost, RF also performed well, accuracies 0.943 values 0.987 (GB XGBoost) 0.983 (RF). (ET) exhibited (0.946) among individual models 0.985. SVM LR, while slightly less accurate (0.941 0.860, respectively), provided valuable insights, achieving 0.972 LR 0.935. The effectively delineated into five zones (very low, moderate, high, very high), high concentrated Darjeeling Kalimpong subdivisions. These are influenced intense rainfall, unstable geological structures, anthropogenic activities like deforestation urbanization. Notably, ET, RF, GB, XGBoost demonstrated efficiency feature selection, requiring fewer input variables maintaining performance. establishes benchmark for mapping, providing scalable adaptable geospatial hazard prediction. findings hold implications land-use planning, disaster management, environmental conservation vulnerable regions worldwide.

Language: Английский

---

RSEIFE: A new remote sensing ecological index for simulating the land surface eco-environment

Journal of Environmental Management, Journal Year: 2022, Volume and Issue: 326, P. 116851 - 116851

Published: Nov. 25, 2022

Language: Английский

---

Landslide Susceptibility Model Using Artificial Neural Network (ANN) Approach in Langat River Basin, Selangor, Malaysia

Land, Journal Year: 2022, Volume and Issue: 11(6), P. 833 - 833

Published: June 2, 2022

Landslides are a natural hazard that can endanger human life and cause severe environmental damage. A landslide susceptibility map is essential for planning, managing, preventing landslides occurrences to minimize losses. variety of techniques employed susceptibility; however, their capability differs depending on the studies. The aim research produce Langat River Basin in Selangor, Malaysia, using an Artificial Neural Network (ANN). inventory contained total 140 locations which were randomly separated into training testing with ratio 70:30. Nine conditioning factors selected as model input, including: elevation, slope, aspect, curvature, Topographic Wetness Index (TWI), distance road, river, lithology, rainfall. area under curve (AUC) several statistical measures analyses (sensitivity, specificity, accuracy, positive predictive value, negative value) used validate model. ANN was considered achieved very good results validation assessment, AUC value 0.940 both datasets. This study found rainfall be most crucial factor affecting occurrence Basin, 0.248 weight index, followed by road (0.200) elevation (0.136). showed susceptible located north-east Basin. might useful development planning management prevent

Language: Английский

---

Dynamic landslides susceptibility evaluation in Baihetan Dam area during extensive impoundment by integrating geological model and InSAR observations

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2022, Volume and Issue: 116, P. 103157 - 103157

Published: Dec. 21, 2022

On April 6, 2021, the Baihetan dam launched impoundment, and reservoir water surface elevation dramatically increased from 660 m to 812 until October which may induce large-scale landslides in bank. Accurate susceptibility evaluation during impoundment is crucial for controlling possible disasters taking early evacuation or disaster prevention measures. Although many traditional geological models can accurately evaluate of area, they are inadequate make prompt response quick condition changes bank induced by while InSAR technology provide a dynamic observation monitor small displacement occurring Thus, this study proposes new approach dynamically on banks integrating model observation. The combined stability coefficient area calculated Scoops 3D geotechnical parameters, with slope landslides. comparison between before shows that when 150 m, high risk geohazards increases 14.26 km2. field validation confirms provides an effective accurate landslide evaluation, forms timely geoenvironment caused 150-m level increment impoundment.

Language: Английский

---

Comparative Analysis of Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping: A Case Study in Rize, Turkey

Water, Journal Year: 2023, Volume and Issue: 15(14), P. 2661 - 2661

Published: July 22, 2023

The Eastern Black Sea Region is regarded as the most prone to landslides in Turkey due its geological, geographical, and climatic characteristics. Landslides this region inflict both fatalities significant economic damage. main objective of study was create landslide susceptibility maps (LSMs) using tree-based ensemble learning algorithms for Ardeşen Fındıklı districts Rize Province, which second-most-prone province terms within Region, after Trabzon. In study, Random Forest (RF), Gradient Boosting Machine (GBM), CatBoost, Extreme (XGBoost) were used machine algorithms. Thus, comparing prediction performances these established second aim study. For purpose, 14 conditioning factors LMSs. are: lithology, altitude, land cover, aspect, slope, slope length steepness factor (LS-factor), plan profile curvatures, tree cover density, topographic position index, wetness distance drainage, roads, faults. total data set, includes non-landslide pixels, split into two parts: training set (70%) validation (30%). area under receiver operating characteristic curve (AUC-ROC) method evaluate models. AUC values showed that CatBoost (AUC = 0.988) had highest performance, followed by XGBoost 0.987), RF 0.985), GBM (ACU 0.975) Although models close each other, performed slightly better than other These results especially can be reduce damages area.

Language: Английский

---

An integrated neural network method for landslide susceptibility assessment based on time-series InSAR deformation dynamic features

International Journal of Digital Earth, Journal Year: 2023, Volume and Issue: 17(1)

Published: Dec. 17, 2023

We develop an integrated neural network landslide susceptibility assessment (LSA) method that integrates temporal dynamic features of interferometry synthetic aperture radar (InSAR) deformation data and the spatial influencing factors. construct a time-distributed convolutional (TD-CNN) bidirectional gated recurrent unit (Bi-GRU) to better understand InSAR cumulative deformation, multi-scale (MSCNN) determine factors, parallel unified deep learning model fuse these for LSA. Compared with traditional MSCNN method, accuracy proposed is improved by 1.20%. The performance preferable MSCNN. area under receiver operating characteristic curve (AUC) testing set reaches 0.91. Our LSA results show clearly depicts areas very high landslides. Further, only 10.18% study accurately covers 84.79% historical areas. Subjective consequences objective indicators time-series can make full use characteristics effectively improve reliability

Language: Английский

---