A Decade of Wheat Mapping for Lebanon

2025-04-15

AI Summary

To address the need for decadal winter wheat monitoring in Lebanon, this study proposes an end-to-end remote sensing-based field-level wheat mapping method. Methodologically, we introduce a lightweight model integrating a novel Temporal-Spatial Vision Transformer (TSViT) with Parameter-Efficient Fine-Tuning (PEFT), and design a new post-processing pipeline grounded in the Fields of The World (FTW) framework to mitigate aggregation errors over small parcels and achieve semantically consistent, geometrically accurate field boundary delineation. Experimental results demonstrate significant improvements in both boundary precision and field-level classification accuracy. The approach successfully generated a high-consistency, temporally continuous ten-year (2014–2023) winter wheat distribution map for Lebanon, enabling robust crop rotation pattern identification and supporting long-term food security policy decisions.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Wheat accounts for approximately 20% of the world's caloric intake, making it a vital component of global food security. Given this importance, mapping wheat fields plays a crucial role in enabling various stakeholders, including policy makers, researchers, and agricultural organizations, to make informed decisions regarding food security, supply chain management, and resource allocation. In this paper, we tackle the problem of accurately mapping wheat fields out of satellite images by introducing an improved pipeline for winter wheat segmentation, as well as presenting a case study on a decade-long analysis of wheat mapping in Lebanon. We integrate a Temporal Spatial Vision Transformer (TSViT) with Parameter-Efficient Fine Tuning (PEFT) and a novel post-processing pipeline based on the Fields of The World (FTW) framework. Our proposed pipeline addresses key challenges encountered in existing approaches, such as the clustering of small agricultural parcels in a single large field. By merging wheat segmentation with precise field boundary extraction, our method produces geometrically coherent and semantically rich maps that enable us to perform in-depth analysis such as tracking crop rotation pattern over years. Extensive evaluations demonstrate improved boundary delineation and field-level precision, establishing the potential of the proposed framework in operational agricultural monitoring and historical trend analysis. By allowing for accurate mapping of wheat fields, this work lays the foundation for a range of critical studies and future advances, including crop monitoring and yield estimation.

Problem

• Accurately mapping wheat fields from satellite images
• Improving winter wheat segmentation and boundary extraction
• Enabling long-term agricultural monitoring and trend analysis

Innovation

• TSViT with PEFT for wheat segmentation
• FTW framework for post-processing pipeline
• Merge segmentation with boundary extraction