Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation models

TL;DR

This paper presents a novel approach combining crowdsourced labels with advanced AI models, specifically Mixed Vision Transformers and ConvNeXt, to accurately detect kelp forests in Landsat satellite images, enhancing environmental monitoring capabilities.

Contribution

It introduces a new pipeline integrating crowdsourced data with state-of-the-art AI models for kelp detection, achieving high accuracy and low false positives in medium-resolution satellite imagery.

Findings

Ensemble of MIT and ConvNeXt models improves detection accuracy.

U-Net identified as the best segmentation architecture.

High detection rate with about 75% of kelp pixels correctly identified.

Abstract

Kelp forests, as foundation species, are vital to marine ecosystems, providing essential food and habitat for numerous organisms. This study explores the integration of crowdsourced labels with advanced artificial intelligence models to develop a fast and accurate kelp canopy detection pipeline using Landsat images. Building on the success of a machine learning competition, where this approach ranked third and performed consistently well on both local validation and public and private leaderboards, the research highlights the effectiveness of combining Mixed Vision Transformers (MIT) with ConvNeXt models. Training these models on various image sizes significantly enhanced the accuracy of the ensemble results. U-Net emerged as the best segmentation architecture, with UpperNet also contributing to the final ensemble. Key Landsat bands, such as ShortWave InfraRed (SWIR1) and Near-InfraRed (NIR), were crucial while altitude data was used in postprocessing to eliminate false positives on land. The methodology achieved a high detection rate, accurately identifying about three out of four pixels containing kelp canopy while keeping false positives low. Despite the medium resolution of Landsat satellites, their extensive historical coverage makes them effective for studying kelp forests. This work also underscores the potential of combining machine learning models with crowdsourced data for effective and scalable environmental monitoring. All running code for training all models and inference can be found at https://github.com/IoannisNasios/Kelp_Forests.