Time-Series Remote Sensing for Land Use/Cover Change Training Course

Course Title: Time-Series Remote Sensing for Land Use/Cover Change Training Course

Executive Summary

This intensive two-week course provides participants with a comprehensive understanding of time-series remote sensing techniques for land use and land cover change analysis. Participants will learn the theoretical foundations of remote sensing, focusing on time-series data acquisition, pre-processing, and analysis. The course covers various change detection methods, classification algorithms, and accuracy assessment techniques relevant to land use/cover change mapping and monitoring. Hands-on exercises using industry-standard software will enable participants to apply these techniques to real-world datasets. By the end of the course, participants will be equipped with the skills to analyze time-series remote sensing data effectively and contribute to informed decision-making regarding land resource management and environmental monitoring.

Introduction

Land use and land cover (LULC) change is a critical aspect of global environmental change, impacting biodiversity, climate, and ecosystem services. Remote sensing provides a powerful tool for monitoring and analyzing LULC dynamics over space and time. Time-series remote sensing, which involves the analysis of satellite imagery acquired at multiple time points, offers valuable insights into LULC change processes. This two-week training course is designed to equip participants with the knowledge and skills necessary to effectively utilize time-series remote sensing data for LULC change analysis. The course will cover the fundamental principles of remote sensing, data pre-processing techniques, change detection algorithms, classification methods, and accuracy assessment procedures. Participants will gain hands-on experience using industry-standard software to process and analyze time-series remote sensing data, enabling them to contribute to informed decision-making in land resource management and environmental monitoring.

Course Outcomes

• Understand the theoretical foundations of remote sensing and time-series analysis.
• Perform data pre-processing steps, including atmospheric correction and geometric correction.
• Apply various change detection methods to identify areas of LULC change.
• Implement classification algorithms for LULC mapping.
• Assess the accuracy of LULC change maps.
• Utilize industry-standard software for time-series remote sensing analysis.
• Interpret results and communicate findings effectively.

Training Methodologies

• Interactive lectures and presentations.
• Hands-on exercises using remote sensing software.
• Case study analysis of real-world LULC change projects.
• Group discussions and problem-solving sessions.
• Demonstrations of data processing and analysis workflows.
• Individual project assignments.
• Guest lectures from experts in the field.

Benefits to Participants

• Enhanced knowledge of time-series remote sensing techniques.
• Improved skills in data processing and analysis.
• Increased proficiency in using remote sensing software.
• Ability to generate accurate LULC change maps.
• Better understanding of LULC change processes.
• Enhanced ability to contribute to informed decision-making.
• Career advancement opportunities in remote sensing and GIS.

Benefits to Sending Organization

• Improved capacity for LULC monitoring and analysis.
• Enhanced ability to assess environmental impacts.
• More informed decision-making regarding land resource management.
• Improved compliance with environmental regulations.
• Enhanced ability to track progress towards sustainable development goals.
• Improved access to reliable and up-to-date LULC information.
• Increased efficiency in data collection and analysis.

Target Participants

• Remote sensing specialists.
• GIS analysts.
• Environmental scientists.
• Land resource managers.
• Urban planners.
• Agricultural extension officers.
• Researchers in related fields.

Week 1: Foundations of Remote Sensing and Time-Series Analysis

Module 1: Introduction to Remote Sensing

1. Principles of remote sensing.
2. Electromagnetic spectrum.
3. Remote sensing platforms and sensors.
4. Spatial, spectral, temporal, and radiometric resolution.
5. Data formats and sources.
6. Overview of remote sensing applications.
7. Introduction to LULC change analysis.

Module 2: Time-Series Data Acquisition and Pre-processing

1. Sources of time-series remote sensing data (Landsat, Sentinel, MODIS).
2. Data download and organization.
3. Atmospheric correction techniques.
4. Geometric correction and registration.
5. Image enhancement and filtering.
6. Cloud masking and removal.
7. Data stacking and mosaicking.

Module 3: Change Detection Methods

1. Principles of change detection.
2. Image differencing and rationing.
3. Vegetation indices for change detection (NDVI, EVI).
4. Change vector analysis.
5. Principal component analysis (PCA).
6. Post-classification comparison.
7. Hybrid change detection techniques.

Module 4: Classification Algorithms for LULC Mapping

1. Supervised and unsupervised classification.
2. Maximum likelihood classification.
3. Support vector machines (SVM).
4. Random forest classification.
5. Object-based image analysis (OBIA).
6. Spectral mixture analysis.
7. Selection of training data and feature extraction.

Module 5: Accuracy Assessment

1. Principles of accuracy assessment.
2. Error matrix and confusion matrix.
3. Overall accuracy, producer’s accuracy, and user’s accuracy.
4. Kappa coefficient.
5. Sampling design for accuracy assessment.
6. Ground truth data collection.
7. Error analysis and interpretation.

Week 2: Advanced Techniques and Applications

Module 6: Time-Series Analysis Techniques

1. Time-series decomposition.
2. Trend analysis and seasonality.
3. Smoothing techniques.
4. Time-series classification.
5. Dynamic time warping.
6. Spectral trajectory analysis.
7. Change point detection.

Module 7: Advanced Change Detection Methods

1. Continuous change detection and classification (CCDC).
2. LandTrendr.
3. Vegetation change tracker (VCT).
4. Time-series segmentation.
5. Machine learning for change detection.
6. Deep learning for change detection.
7. Integration of multiple data sources.

Module 8: LULC Change Modeling

1. Cellular automata models.
2. Agent-based models.
3. Markov chain models.
4. SLEUTH model.
5. CLUE-S model.
6. Integration of remote sensing data with LULC change models.
7. Scenario analysis and future projections.

Module 9: Applications of Time-Series Remote Sensing

1. Deforestation monitoring.
2. Urban expansion analysis.
3. Agricultural land use change.
4. Rangeland monitoring.
5. Wetland change detection.
6. Climate change impacts assessment.
7. Disaster monitoring and assessment.

Module 10: Project Presentations and Course Wrap-up

1. Participant project presentations.
2. Discussion of project findings.
3. Course review and summary.
4. Future directions in time-series remote sensing.
5. Resources and tools for continued learning.
6. Q&A session.
7. Course evaluation and feedback.

Action Plan for Implementation

1. Identify a specific LULC change issue relevant to your work.
2. Collect and pre-process time-series remote sensing data for the study area.
3. Apply appropriate change detection and classification techniques.
4. Conduct accuracy assessment of the results.
5. Interpret the findings and communicate them effectively.
6. Develop recommendations for addressing the LULC change issue.
7. Implement the recommendations and monitor their effectiveness.