[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121372-en":3,"doc-seo-121372-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},121372,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Assessing food production systems using machine learning and remote sensing","Understanding and monitoring global agricultural activity, especially under rapid climate change, supports food-supply prediction, subsidy allocation, and environmental monitoring. Advances in computer vision and satellite image acquisition enable large-scale extraction of planetary knowledge. Satellites offer global coverage at low marginal cost, but many regions lack ground-truth labels, limiting supervised machine learning training—particularly in developing countries. This thesis develops self- and semi-supervised crop mapping, then applies causal learning for cover crop impacts and introduces EngScotCrop.","Assessing food production systems using machine learning and remote  \nsensing  \nSamuel James Bancroft  \nSubmitted in accordance with the requirements for the degree of PhD Earth Observation  \nThe University of Leeds  \nICAS  \nSchool of Earth and Environment  \nOctober 2024  \nAbstract  \nUnderstanding and monitoring global agricultural activity, especially in the face of a rapidly changing climate, has applications ranging from food supply predictions to subsidy allocation and environmental monitoring. Rapid advancements in computer vision and satellite imagery acquisition present opportunities to extract planetary knowledge automatically and at large scale. Satellites provide global coverage at relatively low marginal cost. However, many regions lack ground truth labels essential for training machine learning models, which remains a signi􀀌cant challenge, particularly in developing countries. Bridging this label gap is critical for e􀀋ective agricultural monitoring and decision-making.  \nThis thesis 􀀌rst explores self- and semi-supervised learning strategies for crop type mapping:  \nThe 􀀌rst approach involves using generative joint energy-based models to improve feature extraction and model performance with limited labelled data. These models can e􀀎ciently handle limited labelled data by learning better feature representations from the abundant unlabelled data. This is achieved through a domain-agnostic approach, meaning the techniques are not tailored to speci􀀌c types of data and can be applied broadly across various remote sensing datasets.  \nThe second approach employs multi-task learning, incorporating physical and biological characteristics of crops derived from the PROSAIL radiative transfer model. By leveraging this domain-speci􀀌c information, the model gains a deeper understanding of the crop growth processes, leading to improved generalisation across di􀀋erent crop types  \nand environmental conditions. This allows the model to simultaneously learn multiple related tasks, enhancing its ability to capture complex interactions related to crop types and traits within the data.  \nThe 􀀌nal chapter extends these methodologies to practical applications, focussing on cover crop mapping. Cover crops play a crucial role in sustainable agriculture by improving soil health, reducing erosion, and enhancing crop yields. By creating detailed cover crop maps, this research assesses the e􀀋ectiveness and impacts of cover crops on agricultural productivity. In this chapter we use causal machine learning to estimate impacts on net primary productivity (NPP) . This research provides valuable insights into sustainable agricultural practices. This integration of machine learning, remote sensing, and causal inference techniques o􀀋ers a comprehensive toolset for assessing and optimising future food production systems.  \nThis research also presents EngScotCrop, a new benchmark crop classi􀀌cation dataset, a large-scale open-access dataset of multimodal satellite image time series alongside agricultural parcel boundaries (UKFields) . This thesis aims to inspire further research into increasingly accurate agricultural maps at larger spatial scales, supporting sustainable development.  \nIntellectual Property  \nThe candidate con􀀌rms that the work submitted is their own and that appropriate credit has been given where reference has been made to the work of others.  \nThis copy has been supplied on the understanding that it is copyright material and that no quotation from the thesis may be published without proper acknowledgement.  \n© 2024 The University of Leeds, Samuel James Bancroft  \nAcknowledgements  \nI'd like to thank my supervisors: Andy Challinor, Netta Cohen, Anthony Cohn, and Julia Chatterton for their guidance and patience throughout the course of my PhD. I would also like to thank the Climate Impacts Group at the University of Leeds for fascinating discussions, valued feedback, and useful advice.  \nI'm grateful to have shared this experience with","cbCaif3qwOoMXxES","https://ap.wps.com/l/cbCaif3qwOoMXxES","pdf",23405855,1,193,"English","en",105,"# Introduction\n## History of agricultural monitoring\n## Motivation and Overview of Thesis\n## Outline and Contributions\n## Relevance to Science and Society\n# Background\n## Overview\n## Role of Remote Sensing in Improving Food Security\n## Earth Observation for Time Series Analysis\n## Machine and Deep Learning\n## Challenges in Crop Type Classification\n## Moving beyond fully-supervised Crop Type Classi􀀌cation\n## Unsupervised Learning\n## Weakly Supervised Learning\n## Transfer Learning\n## Meta Learning\n## Semi-supervised Learning\n## Multimodal learning","[{\"question\":\"Why is label availability a key challenge for agricultural monitoring with machine learning?\",\"answer\":\"Many regions lack ground-truth labels needed to train supervised machine learning models, making effective agricultural monitoring difficult, especially in developing countries.\"},{\"question\":\"What self- and semi-supervised approaches are explored for crop type mapping?\",\"answer\":\"The thesis investigates generative joint energy-based models for better feature extraction with limited labeled data, and a multi-task learning approach using PROSAIL-derived physical and biological crop characteristics.\"},{\"question\":\"How does the thesis extend the methods to practical applications?\",\"answer\":\"It focuses on cover crop mapping and uses causal machine learning to estimate impacts on net primary productivity (NPP), evaluating how cover crops affect agricultural productivity.\"}]","Assessing food production systems using machine learning and remote sensing | PDF",1785735298,486,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"assessing-food-production-systems-using-machine-learning-and-remote-sensing","",{"@graph":36,"@context":85},[37,54,68],{"@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/assessing-food-production-systems-using-machine-learning-and-remote-sensing/121372/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is label availability a key challenge for agricultural monitoring with machine learning?","Question",{"text":75,"@type":76},"Many regions lack ground-truth labels needed to train supervised machine learning models, making effective agricultural monitoring difficult, especially in developing countries.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What self- and semi-supervised approaches are explored for crop type mapping?",{"text":80,"@type":76},"The thesis investigates generative joint energy-based models for better feature extraction with limited labeled data, and a multi-task learning approach using PROSAIL-derived physical and biological crop characteristics.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis extend the methods to practical applications?",{"text":84,"@type":76},"It focuses on cover crop mapping and uses causal machine learning to estimate impacts on net primary productivity (NPP), evaluating how cover crops affect agricultural productivity.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]