[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123953-en":3,"doc-seo-123953-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123953,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Predicting Sea Surface Wave and Wind Parameters from Satellite Radar Images using Machine Learning","Accurate wave and wind forecasts over oceans are essential for many marine activities, yet buoy deployments are limited, making broader coverage necessary. This project leverages Sentinel-1 SAR imagery to learn the relationship between radar backscatter patterns and buoy-measured significant wave height and wind speed. Using buoy data from 2021, corresponding 2 km×2 km SAR sub-images were extracted and processed into feature sets for supervised learning. Two deep learning regression models jointly predict both variables, achieving RMSE of 0.553 m and 1.573 m/s with features alone, and 0.459 m and 1.658 m/s with sub-images plus features.","Predicting sea surface wave and wind parameters from satellite radar images using machine learning  \nMaster’s thesis in Computer science and engineering  \nFilip Borg  \nAxel Brobeck  \nDepartment of Space, Earth and Environment CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2023  \nMaster’s thesis 2023  \nPredicting sea surface wave and wind parameters from satellite radar images using machine learning  \nFilip Borg  \nAxel Brobeck  \nDepartment of Space, Earth and Environment Chalmers University of Technology Gothenburg, Sweden 2023  \nPredicting sea surface wave and wind parameters from satellite radar images using machine learning  \nFilip Borg Axel Brobeck  \n© Filip Borg & Axel Brobeck, 2023 .  \nSupervisor: Anis Elyouncha, Space, Earth and Environment  \nSupervisor: Adrià Amell, Space, Earth and Environment  \nExaminer: Leif Eriksson, Space, Earth and Environment  \nMaster’s Thesis 2023  \nDepartment of Space, Earth and Environment Chalmers University of Technology SE-412 96 Gothenburg  \nTelephone +46 31 772 1000  \nTypeset in LATEX  \nGothenburg, Sweden 2023  \nPredicting sea surface wave and wind parameters from satellite radar images using machine learning  \nFilip Borg Axel Brobeck  \nDepartment of Space, Earth and Environment Chalmers University of Technology  \nAbstract  \nAccurate predictions of wave and wind parameters over oceans are crucial for various marine operations. Although buoys provide accurate measurements, their deployment is limited, which necessitates the exploration of alternative data sources. Sentinel-1, a satellite mission capturing Synthetic Aperture Radar (SAR) images with high coverage, presents a promising opportunity. However, establishing the relationship between SAR images and wave/wind parameters is not straightforward. This project aims to develop a machine learning model that can effectively extract this relationship.  \nTo accomplish this, data from all available buoys measuring significant wave height and wind speed in the year 2021 were utilized. The corresponding SAR images were located, and 2 km×2 km sub-images were extracted around each buoy. From each sub-image, a set of features were extracted. These sub-images and features served as input to train machine learning models capable of predicting buoy measurements, supplemented with model data as necessary.  \nThe project presents two final deep learning models: one utilizing only the extracted features and another employing both the sub-images and features. These multi-class regression models simultaneously predict significant wave height and wind speed. The model using only features achieved a Root Mean Square Error (RMSE) of 0.553 m for significant wave height and 1.573 m/s for wind speed. The model incorporating both sub-images and features achieved an RMSE of 0.459 m for significant wave height and 1.658 m/s for wind speed.  \nThe code for the project can be found on [https://github.com/SEE-GEO/sarssw](https://github.com/SEE-GEO/sarssw).  \nKeywords: Machine Learning, Computer Vision, Synthetic Aperture Radar, Significant Wave Height, Wind Speed, Radar, Master Thesis, Chalmers University of Technology  \nAcknowledgements  \nWe would like to thank our supervisors Anis Elyouncha and Adrià Amell for their valuable feedback and insightful discussions.  \nLeif Eriksson also deserves our thanks for his dedicated service as our examiner.  \nWe would also like to thank ESA and their Copernicus program for making the ERA5 [1] model data and the Sentinel-1 SAR data available.  \nThe Copernicus [2] Sentinel-1 data for this project has been retrieved from NASA’s Alaska Satellite Facility Distributed Active Archive Center (ASF DAAC) [3], processed by ESA.  \nThis study has been conducted using E.U. Copernicus Marine Service Information; Global Ocean- In-Situ Near-Real-Time Observations [4] & Global Ocean Hourly Reprocessed Sea Surface Wind and Stress from Scatterometer and Model [5] .  \nFilip Borg & Axel Brobeck, Gothenburg, 2023-09-10  \nContents  \nList of Figures","cbCait8ErOPAz27j","https://ap.wps.com/l/cbCait8ErOPAz27j","pdf",12309230,1,68,"English","en",105,"# Introduction\n## Aim\n## Objectives\n## Limitations\n# Theory\n## Significant Wave Height and Wind Speed Interactions\n## Synthetic Aperture Radar and Sentinel-1\n## Data Sources\n## Machine Learning\n# Methods\n## Data Pipeline\n## Collocating SAR-images with Buoy Data\n## Extracting Sub-images from SAR-Images\n## Features","[{\"question\":\"Why are buoys not sufficient for wave and wind parameter prediction?\",\"answer\":\"Buoys provide accurate measurements, but their deployment coverage is limited. This motivates using satellite data with broader observation capability.\"},{\"question\":\"What satellite data and targets does the project use?\",\"answer\":\"The project uses Sentinel-1 Synthetic Aperture Radar (SAR) images and aims to predict significant wave height and wind speed measured by buoys.\"},{\"question\":\"How are SAR inputs prepared for the machine learning models?\",\"answer\":\"For each buoy, corresponding SAR images are located and 2 km×2 km sub-images are extracted. Features are extracted from each sub-image, and models are trained using these features, optionally alongside the sub-images.\"}]","Predicting Sea Surface Wave and Wind Parameters from Satellite Radar Images using Machine Learning | PDF",1785819411,171,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"predicting-sea-surface-wave-and-wind-parameters-from-satellite-radar-images-using-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-sea-surface-wave-and-wind-parameters-from-satellite-radar-images-using-machine-learning/123953/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are buoys not sufficient for wave and wind parameter prediction?","Question",{"text":76,"@type":77},"Buoys provide accurate measurements, but their deployment coverage is limited. This motivates using satellite data with broader observation capability.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What satellite data and targets does the project use?",{"text":81,"@type":77},"The project uses Sentinel-1 Synthetic Aperture Radar (SAR) images and aims to predict significant wave height and wind speed measured by buoys.",{"name":83,"@type":74,"acceptedAnswer":84},"How are SAR inputs prepared for the machine learning models?",{"text":85,"@type":77},"For each buoy, corresponding SAR images are located and 2 km×2 km sub-images are extracted. Features are extracted from each sub-image, and models are trained using these features, optionally alongside the sub-images.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]