BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Talks.cam//talks.cam.ac.uk// X-WR-CALNAME:Talks.cam BEGIN:VEVENT SUMMARY:Towards Improved Crop Type Classification: a Compact Representatio n Approach for Smallholder Agriculture (TESSERA application) - Madeline Li saius\, University of Cambridge DTSTART:20250605T120000Z DTEND:20250605T130000Z UID:TALK232996@talks.cam.ac.uk CONTACT:114742 DESCRIPTION:*Abstract*\n\nSatellite-based monitoring of smallholder agricu lture is an important tool for food security but existing approaches are n either accessible nor effective for small plot field systems. To address t hese issues\, crop type classification using representations generated by a global foundation model\, TESSERA\, is compared to best classification a pproaches in the literature. We present a novel approach to smallholder pl ots and compare representation based methods to raw data based methods for crop type classification in challenging environments. We find that our re presentation based approach offers a triple win: 1) consistent and statist ically significant performance improvement over current methods\, 2) great er simplicity due to the elimination of cloud masking and feature engineer ing\, and 3) the reduction of computational cost. Our representation based approach achieves significantly higher F1 scores in the classification of 7 crop types for small fields in Austria for 5 classes (over 10% improvem ent in one case) and comparable F1 scores for two classes\, and the best r epresentation-based methods use 5% and 8% of compute compared to the best raw data method. These results indicate that representations are an effect ive approach for crop type classification tasks for small field systems.\n \n*Bio*\n\nMadeline Lisaius received BS and MS degrees in Earth Systems wi th a focus on environmental spatial statistics and remote sensing from Sta nford University\, Stanford\, California\, USA as well as MRes degree in E nvironmental Data Science from the University of Cambridge\, Cambridge\, U K. She is working towards the PhD in the Department of Computer Science an d Technology at the University of Cambridge. She is focused on topics of f ood security and environmental justice\, remote sensing\, and machine lear ning. \n\n LOCATION:Room GS15 at the William Gates Building and on Zoom: https://cl-c am-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&\;fr om=addon END:VEVENT END:VCALENDAR