Weakly Supervised Ephemeral Gully Detection In Remote Sensing Images Using Vision Language Models

2025-11-17

AI Summary

Ephemeral gullies—short-lived, intermittently active erosion features—pose significant challenges for automated detection due to their transient nature and severe scarcity of high-quality annotations. To address this, we propose the first weakly supervised detection framework specifically designed for ephemeral gully identification. Our method leverages vision-language models (VLMs) to generate noisy pseudo-labels, establishes a teacher–student collaborative training paradigm, and introduces a noise-aware loss function to mitigate label noise. Furthermore, we construct the first large-scale semi-supervised dataset for gully detection, comprising over 18,000 high-resolution remote sensing images spanning 13 years. Extensive experiments demonstrate that our approach substantially outperforms both pure VLM-based baselines and fully supervised benchmarks, achieving higher detection accuracy and improved generalization while drastically reducing annotation effort. This work provides a scalable, cost-effective technical pathway for intelligent soil erosion monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Among soil erosion problems, Ephemeral Gullies are one of the most concerning phenomena occurring in agricultural fields. Their short temporal cycles increase the difficulty in automatically detecting them using classical computer vision approaches and remote sensing. Also, due to scarcity of and the difficulty in producing accurate labeled data, automatic detection of ephemeral gullies using Machine Learning is limited to zero-shot approaches which are hard to implement. To overcome these challenges, we present the first weakly supervised pipeline for detection of ephemeral gullies. Our method relies on remote sensing and uses Vision Language Models (VLMs) to drastically reduce the labor-intensive task of manual labeling. In order to achieve that, the method exploits: 1) the knowledge embedded in the VLM's pretraining; 2) a teacher-student model where the teacher learns from noisy labels coming from the VLMs, and the student learns by weak supervision using teacher-generate labels and a noise-aware loss function. We also make available the first-of-its-kind dataset for semi-supervised detection of ephemeral gully from remote-sensed images. The dataset consists of a number of locations labeled by a group of soil and plant scientists, as well as a large number of unlabeled locations. The dataset represent more than 18,000 high-resolution remote-sensing images obtained over the course of 13 years. Our experimental results demonstrate the validity of our approach by showing superior performances compared to VLMs and the label model itself when using weak supervision to train an student model. The code and dataset for this work are made publicly available.

Problem

• Automatically detecting ephemeral gullies in agricultural fields using remote sensing
• Overcoming scarcity of accurate labeled data for machine learning detection
• Reducing labor-intensive manual labeling through weakly supervised approaches

Innovation

• Uses Vision Language Models to reduce manual labeling
• Implements teacher-student model with weak supervision
• Employs noise-aware loss function for training student model