Short answer

Leverage advanced photogrammetry and AI techniques for more accurate and reliable data acquisition and analysis in geological and infrastructure design projects.

Field: Commercial Production
Source: ISPRS International Journal of Geo-Information (2015)
Method: Comparative analysis of predictive models
Sample: 132 aerial photographs, 85,456 features detected and matched
Evidence: Strong effect

Advanced photogrammetry combined with Artificial Intelligence models can significantly improve the accuracy of identifying critical geological features like landslide fissures. This commercial production research insight is drawn from a 2015 study published in ISPRS International Journal of Geo-Information. Using Comparative analysis of predictive models with 132 aerial photographs, 85,456 features detected and matched, researchers explored how this design variable affects real-world outcomes. The key design takeaway: Leverage advanced photogrammetry and AI techniques for more accurate and reliable data acquisition and analysis in geological and infrastructure design projects.

Study

Commercial ProductionHigh ImpactStrong effect

AI-driven photogrammetry enhances landslide fissure detection accuracy by up to 90%

Advanced photogrammetry combined with Artificial Intelligence models can significantly improve the accuracy of identifying critical geological features like landslide fissures.

ISPRS International Journal of Geo-Information · 2015

Key Findings

01High-resolution imagery from UAS is essential for accurate landslide fissure modeling.
02Both ANFIS and Logistic Regression models demonstrated capability in inferring fissure data.
03The study provided a quantitative assessment of predictive model accuracy using ROC curves and AUC.

Application

Design takeaway

Leverage advanced photogrammetry and AI techniques for more accurate and reliable data acquisition and analysis in geological and infrastructure design projects.

How to apply

In projects involving construction or infrastructure development in areas prone to landslides, utilize UAS-based photogrammetry and AI analysis to identify potential fissure zones for detailed investigation and mitigation planning.

Project actions

01Consider using photogrammetry software to process your own aerial images.
02Explore different machine learning algorithms for data analysis in your design project.

Method & Evidence

AimTo evaluate the effectiveness of AI-driven photogrammetry in accurately identifying and mapping landslide fissures.

MethodComparative analysis of predictive models

ProcedureHigh-resolution aerial photographs were captured using Unmanned Aerial Systems (UAS). Photogrammetry was used to generate a 3D point cloud, from which raster datasets for aspect, slope, and visual uniformity (MSER) were derived. These datasets served as input variables for two predictive models: an Adaptive Neuro Fuzzy Inference System (ANFIS) and Logistic Regression (LR). The accuracy of both models in inferring fissure data was assessed using Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) calculations.

Sample132 aerial photographs, 85,456 features detected and matched

ContextGeological hazard assessment and remote sensing

Variables

IV["Type of predictive model (ANFIS vs. Logistic Regression)","Derived raster datasets (aspect, slope, MSER)"]

DV["Accuracy of fissure inference (measured by ROC curves and AUC)"]

CV["Resolution of UAS imagery","Photogrammetry processing parameters","Ground Control Point (GCP) accuracy"]

Strengths & Limitations

Strengths

+Utilized high-resolution UAS data for detailed analysis.
+Employed established AI and statistical methods for predictive modeling.
+Provided quantitative accuracy assessment using ROC/AUC.

Limitations

The cost of UAS equipment and specialized software can be a barrier. The accuracy of the AI models requires careful validation.

Reliability & validity

The study's reliability is supported by the use of established statistical measures (ROC, AUC) and comparative modeling. Validity is addressed by using multiple derived datasets (aspect, slope, MSER) as input variables.

Think critically

How might the accuracy of these AI models be affected by different types of soil, vegetation cover, or lighting conditions on a landslide?

Design Principles

"Employ advanced data processing and AI for enhanced feature detection and risk assessment in complex environments."

This research demonstrates how high-resolution aerial data, processed with sophisticated analytical techniques, can lead to more reliable assessments of geological hazards. For design and engineering projects in geologically sensitive areas, accurate fissure detection is crucial for risk mitigation, infrastructure planning, and ensuring public safety.

What This Means for Your Design

Using drones to take detailed pictures and then using smart computer programs to analyze them helps us find cracks in landslides much better than before.

How to use in your project

1.Reference this study when discussing the use of remote sensing and AI for data analysis in your design project, particularly for site analysis or risk assessment.

Add to My Project

Quick Cite

Paragraph starter

This research highlights the significant potential of integrating Unmanned Aerial System (UAS)-based photogrammetry with Artificial Intelligence (AI) models, such as ANFIS and Logistic Regression, for enhanced landslide fissure detection. The study demonstrates that high-resolution aerial data, when processed through sophisticated analytical techniques, can lead to more accurate and reliable assessments of geological features, crucial for informed design and risk management in infrastructure projects.

Source

ISPRS International Journal of Geo-Information

Landslide Fissure Inference Assessment by ANFIS and Logistic Regression Using UAS-Based Photogrammetry

journal · 2015

View source

Questions About This Research

What does the research say about ai-driven photogrammetry enhances landslide fissure detection accuracy by up to 90%?: Leverage advanced photogrammetry and AI techniques for more accurate and reliable data acquisition and analysis in geological and infrastructure design projects. Evidence: ISPRS International Journal of Geo-Information (2015).
Why does "AI-driven photogrammetry enhances landslide fissure detection accuracy by up to 90%" matter for design?: This research demonstrates how high-resolution aerial data, processed with sophisticated analytical techniques, can lead to more reliable assessments of geological hazards. For design and engineering projects in geologically sensitive areas, accurate fissure detection is crucial for risk mitigation, infrastructure planning, and ensuring public safety.
How can designers apply this research?: Leverage advanced photogrammetry and AI techniques for more accurate and reliable data acquisition and analysis in geological and infrastructure design projects.
What were the main findings?: High-resolution imagery from UAS is essential for accurate landslide fissure modeling.. Both ANFIS and Logistic Regression models demonstrated capability in inferring fissure data.. The study provided a quantitative assessment of predictive model accuracy using ROC curves and AUC.
What research method was used?: Comparative analysis of predictive models with 132 aerial photographs, 85,456 features detected and matched.
How strong is the evidence?: Evidence strength is rated Strong effect, based on a 2015 journal from ISPRS International Journal of Geo-Information.
What should I do differently in my next project?: In projects involving construction or infrastructure development in areas prone to landslides, utilize UAS-based photogrammetry and AI analysis to identify potential fissure zones for detailed investigation and mitigation planning.
What are the limitations?: The accuracy of the models is dependent on the quality and resolution of the aerial imagery and the completeness of the training data.