TerraTrace - Spatio-Temporal Vegetation Signatures for Land Use Analytics

2025-02-25

Workshop on Mobile Computing Systems and Applications

AI Summary

Accurate discrimination among cropland, orchard, and forest remains challenging for climate change monitoring due to spectral and phenological similarities. Method: We propose a novel land-use semantic parsing paradigm leveraging NDVI time-series dynamic features. Using a large-scale, 500-m-resolution NDVI time series dataset (2020–2023) comprising over 70 million points across California, we identify crop-specific NDVI temporal signatures exhibiting global consistency and strong discriminative power for agricultural and forest classes. Our approach integrates remote sensing time-series modeling, scalable geospatial processing, and an LLM-powered natural language interface for intuitive querying. Contribution/Results: The framework achieves high-accuracy classification of crop types and robust cropland–forest discrimination. It supports interpretable, interactive visual analytics, enabling end-to-end intelligent land-use analysis with transparent decision logic.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Understanding land use over time is critical to tracking events related to climate change, like deforestation. However, satellite-based remote sensing tools which are used for monitoring struggle to differentiate vegetation types in farms and orchards from forests. We observe that metrics such as the Normalized Difference Vegetation Index (NDVI), based on plant photosynthesis, have unique temporal signatures that reflect agricultural practices and seasonal cycles. We analyze yearly NDVI changes on 20 farms for 10 unique crops. Initial results show that NDVI curves are coherent with agricultural practices, are unique to each crop, consistent globally, and can differentiate farms from forests. We develop a novel longitudinal NDVI dataset for the state of California from 2020-2023 with 500~m resolution and over 70 million points. We use this to develop the TerraTrace platform, an end-to-end analytic tool that classifies land use using NDVI signatures and allows users to query the system through an LLM chatbot and graphical interface.

Problem

• Differentiates vegetation types in farms and orchards
• Tracks land use changes over time
• Develops an NDVI-based land classification tool

Innovation

• Uses NDVI temporal signatures
• Develops longitudinal NDVI dataset
• Implements LLM chatbot interface