Mapping Farmed Landscapes from Remote Sensing

2025-06-16

AI Summary

Large-scale, high-resolution ecological mapping remains a critical bottleneck for landscape-scale ecological management in global agriculture, hindering progress toward biodiversity targets. To address this, we developed Farmscapes—the first nationwide, 25-cm-resolution ecological landscape map of England—systematically delineating key linear (e.g., hedgerows, stone walls) and areal (e.g., woodlands, arable fields) ecological features. We propose a novel deep learning–based semantic segmentation model specifically optimized for linear habitat elements, trained on 942 expertly annotated aerial images and deployed via Google Earth Engine for open access. The model achieves F1-scores of 96% for woodland, 95% for arable land, and 72% for hedgerows. Farmscapes is publicly available and already supports EU Biodiversity Strategy monitoring, habitat restoration planning, and landscape connectivity assessment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Efficient ML / Green AI
• Search and Optimization: Algorithm Configuration

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Effective management of agricultural landscapes is critical for meeting global biodiversity targets, but efforts are hampered by the absence of detailed, large-scale ecological maps. To address this, we introduce Farmscapes, the first large-scale (covering most of England), high-resolution (25cm) map of rural landscape features, including ecologically vital elements like hedgerows, woodlands, and stone walls. This map was generated using a deep learning segmentation model trained on a novel, dataset of 942 manually annotated tiles derived from aerial imagery. Our model accurately identifies key habitats, achieving high f1-scores for woodland (96%) and farmed land (95%), and demonstrates strong capability in segmenting linear features, with an F1-score of 72% for hedgerows. By releasing the England-wide map on Google Earth Engine, we provide a powerful, open-access tool for ecologists and policymakers. This work enables data-driven planning for habitat restoration, supports the monitoring of initiatives like the EU Biodiversity Strategy, and lays the foundation for advanced analysis of landscape connectivity.

Problem

• Mapping large-scale rural landscapes for biodiversity management
• Identifying ecologically vital features using deep learning
• Providing open-access tools for habitat restoration planning

Innovation

• Deep learning segmentation model for mapping
• High-resolution 25cm aerial imagery dataset
• Open-access England-wide map on Google Earth Engine