Related Experiment Video
Updated: Jan 20, 2026
06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
2.3K
Improving GIS-based Landslide Susceptibility Assessments with Multi-temporal Remote Sensing and Machine Learning.
Jhe-Syuan Lai1,2, Fuan Tsai3,4
1Department of Civil Engineering, Feng Chia University, Taichung 40724, Taiwan.
Sensors (Basel, Switzerland)
|August 30, 2019
Summary
This study uses machine learning (ML) and satellite data for landslide susceptibility mapping. The developed models achieve high accuracy, exceeding 93% for space-robustness and 75% for time-robustness, proving effective for regional assessments.
Area of Science:
- Geosciences
- Remote Sensing
- Machine Learning
Background:
- Landslide susceptibility assessments are crucial for disaster risk reduction.
- Traditional methods often lack the spatial and temporal resolution needed for dynamic event-based analysis.
- Integrating satellite remote sensing and GIS offers a powerful approach for regional-scale assessments.
Purpose of the Study:
- To develop a systematic approach using machine learning (ML) for multi-temporal and event-based landslide susceptibility assessments.
- To evaluate the effectiveness of the Random Forests (RF) algorithm with different sample ratios and cost-sensitive analysis.
- To assess the spatial and time-robustness of the developed landslide susceptibility models.
Main Methods:
- Utilized satellite remote sensing images and Geographic Information System (GIS) datasets for spatial analysis.
- Applied the Random Forests (RF) algorithm, incorporating cost-sensitive analysis for unbalanced sample ratios.
- Employed space- and time-robustness verification strategies to assess model reliability.
- Derived 14 GIS-based landslide-related factors for model construction.
Main Results:
- Achieved high prediction accuracies, with space-robustness verification exceeding 93% and time-robustness verification exceeding 75% in most cases.
- Demonstrated that multi-temporal models were not significantly affected by variations in sample ratios.
- Cost-sensitive analysis improved prediction results for unbalanced sample datasets.
Conclusions:
- The proposed systematic approach integrating ML, satellite remote sensing, and GIS is effective for regional landslide susceptibility assessment.
- The developed RF models exhibit robust performance in both space and time, providing reliable predictions for future landslide events.
- The methodology offers a valuable tool for enhancing landslide hazard management and mitigation strategies.
Related Concept Videos
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
2.3K
Mime is a flexible computational framework to construct a machine learning-based integration model with elegant performance. Here, we provide a detailed step-by-step procedure for developing predictive models with high accuracy, leveraging complex datasets to identify critical genes associated with disease progression, patient outcomes, and therapeutic response.
2.3K
08:16Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
512
Recent advancements in remotely piloted aircraft systems (RPAS) allow sub-meter resolution, ideal for forest recovery monitoring. Integrating artificial intelligence (AI) enables deeper insights from large remotely sensed datasets. This protocol improves monitoring by supporting more efficient assessment and management of forested lands recovering from...
512
06:16Femtosecond Laser Filaments for Use in Sub-Diffraction-Limited Imaging and Remote Sensing
8.0K
High-intensity femtosecond pulses of laser light can undergo cycles of Kerr self-focusing and plasma defocusing, propagating an intense sub-millimeter-diameter beam over long distances. We describe a technique for generating and using these filaments to perform remote imaging and sensing beyond the classical diffraction limits of linear...
8.0K
04:04Asthma Detection Research Based on Voice Signal Processing and Machine Learning
940
This study employed voice signal analysis and machine learning methods, utilizing MATLAB to extract distinctive voice features for non-invasive early detection of asthma. The Support Vector Machine (SVM) and Random Forest (RF) algorithms demonstrated comparable performance in terms of overall classification accuracy, although SVM may achieve a better balance between sensitivity and...
940
10:58Using GIS to Investigate Urban Forestry
13.7K
Source: Laboratories of Margaret Workman and Kimberly Frye - Depaul University
Urban forests broadly include urban parks, street trees, landscaped boulevards, public gardens, river and coastal promenades, greenways, river corridors, wetlands, nature preserves, natural areas, shelterbelts of trees, and working trees at industrial brownfield sites. The history of urban trees begins with trees as landscape embellishment. Today, urban trees are seen as essential components of city infrastructure...
Urban forests broadly include urban parks, street trees, landscaped boulevards, public gardens, river and coastal promenades, greenways, river corridors, wetlands, nature preserves, natural areas, shelterbelts of trees, and working trees at industrial brownfield sites. The history of urban trees begins with trees as landscape embellishment. Today, urban trees are seen as essential components of city infrastructure...
13.7K
11:38A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation
1.1K
Available pluripotent stem cell (PSC)-to-functional cell differentiation systems are currently impeded by problems of severe line-to-line and batch-to-batch variability. Here, using cardiac differentiation as the main example, we present a protocol to intelligently monitor and modulate the process of PSC differentiation based on image-based machine learning.
1.1K