Joint Super-Resolution and Segmentation for 1-m Impervious Surface Area Mapping in China's Yangtze River Economic Belt

2025-05-08

AI Summary

Addressing the challenge of generating high-accuracy 1-m impervious surface area (ISA) maps directly from freely available Sentinel-2 imagery (10-m resolution) over the complex urban–rural landscapes of the Yangtze River Economic Belt, this paper proposes JointSeg—an end-to-end framework jointly optimizing super-resolution and semantic segmentation. JointSeg introduces a novel progressive super-resolution scheme (10 m → 1 m) coupled with cross-scale feature fusion, integrating multimodal inputs, attention-enhanced modules, and a lightweight segmentation head to preserve textural details while improving classification fidelity. Applied across a 2.2-million-km² region, it produces the first high-resolution ISA-1 product for 2021, achieving an F1-score of 85.71%—a 9.5-percentage-point improvement over bilinear interpolation and outperforming mainstream ISA datasets by 21.43%–61.07%. The framework further enables biennial dynamic monitoring of ISA changes from 2017 to 2023.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Semi-Supervised Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We propose a novel joint framework by integrating super-resolution and segmentation, called JointSeg, which enables the generation of 1-meter ISA maps directly from freely available Sentinel-2 imagery. JointSeg was trained on multimodal cross-resolution inputs, offering a scalable and affordable alternative to traditional approaches. This synergistic design enables gradual resolution enhancement from 10m to 1m while preserving fine-grained spatial textures, and ensures high classification fidelity through effective cross-scale feature fusion. This method has been successfully applied to the Yangtze River Economic Belt (YREB), a region characterized by complex urban-rural patterns and diverse topography. As a result, a comprehensive ISA mapping product for 2021, referred to as ISA-1, was generated, covering an area of over 2.2 million square kilometers. Quantitative comparisons against the 10m ESA WorldCover and other benchmark products reveal that ISA-1 achieves an F1-score of 85.71%, outperforming bilinear-interpolation-based segmentation by 9.5%, and surpassing other ISA datasets by 21.43%-61.07%. In densely urbanized areas (e.g., Suzhou, Nanjing), ISA-1 reduces ISA overestimation through improved discrimination of green spaces and water bodies. Conversely, in mountainous regions (e.g., Ganzi, Zhaotong), it identifies significantly more ISA due to its enhanced ability to detect fragmented anthropogenic features such as rural roads and sparse settlements, demonstrating its robustness across diverse landscapes. Moreover, we present biennial ISA maps from 2017 to 2023, capturing spatiotemporal urbanization dynamics across representative cities. The results highlight distinct regional growth patterns: rapid expansion in upstream cities, moderate growth in midstream regions, and saturation in downstream metropolitan areas.

Problem

• Generating 1-meter impervious surface maps from Sentinel-2 imagery
• Combining super-resolution and segmentation for accurate urban mapping
• Mapping diverse landscapes in Yangtze River Economic Belt

Innovation

• Joint super-resolution and segmentation framework
• Multimodal cross-resolution training inputs
• Gradual resolution enhancement with feature fusion