[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126716-en":3,"doc-seo-126716-105":30,"detail-sidebar-cat-0-en-105":95},{"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},126716,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Physics-assisted machine learning for THz spectroscopy - sensing moisture on plant leaves","Signal processing techniques are crucial for advancing THz time-domain spectroscopy toward practical applications. This work demonstrates physics-assisted machine learning using domain knowledge from light–matter interactions. The target agriculture use case is quantifying free water on plant leaves, known as leaf wetness, a key factor in plant disease development. Experimental THz transmission data are collected across thousands of water patterns, and decision trees and convolutional neural networks are evaluated with physics-motivated choices and tests for generalizability beyond the training distribution.","arXiv :2310 .04056v1 [ ee ss . SP] 6 Oct 2023  \nPhysics-assisted machine learning for THz spectroscopy: sensing moisture on plant leaves  \nMilan Koumans 1 , Daan Meulendijks 1 , Haiko Middeljans 1 , Djero Peeters 1 , Jacob C. Douma2 , and Dook van Mechelen 1,*  \n1 Eindhoven University of Technology, Department of Electrical Engineering, Eindhoven Henrik Casimir Institute, 5600 MB Eindhoven, the Netherlands  \n2 Centre for Crop System Analysis, Wageningen University, 6700 AK Wageningen, the Netherlands  \n* correspondence to: [j.l.m.v.mechelen@tue.nl](j.l.m.v.mechelen@tue.nl)  \nABSTRACT  \nSignal processing techniques are of vital importance to bring THz spectroscopy to a maturity level to reach practical applications. In this work, we illustrate the use of machine learning techniques for THz time-domain spectroscopy assisted by domain knowledge based on light-matter interactions. We aim at the potential agriculture application to determine the amount of free water on plant leaves, so-called leaf wetness. This quantity is important for understanding and predicting plant diseases that need leaf wetness for disease development. The overall transmission of a moist plant leaf for 12,000 distinct water patterns was experimentally acquired using THz time-domain spectroscopy. We report on key insights of applying decision trees and convolutional neural networks to the data using physics-motivated choices. Eventually, we discuss the generalizability of these models to determine leaf wetness after testing them on cases with increasing deviations from the training set.  \nIntroduction  \nThe quest to implement societally and industrially relevant applications of THz technology is impeded by aspects such as costs and performance as compared to alternatives. Despite the wide range of exploratory studies of THz technology since the late 1980s, and the numerous suggested applications, 1 very few products exist that use THz-based techniques. Often demonstrators underperform compared to a cheaper alternative that already exists or that is conveniently adapted to a new application. However, since THz technology is rather new on the market, costs will remain high at least for a while. The only promising way out is to find a novel application for the technology, which it can almost uniquely serve, and for which the business case is strong enough to support the high costs.2 In this case, its overall performance needs to justify its usage. On the hardware side, technological maturity has strongly improved over the last decades, although the progress at an integrated level is lagging.3 On the software side, despite crucial advancements such as model-based analysis that is now widely employed,4 the limitations are generality, robustness, and speed, which are essential for realistic application cases.  \nThe agriculture sector is an area where a multitude of sensing technologies are employed to aid management decisions. Certainly due to this reason, there is a vivid interest in searching for applications in this field where THz spectroscopy can make a difference.5 Globally, pests and pathogens are a big threat to crop production, with yield losses reported in the range of 9 −21 % .6 For some pathogens, such as water molds and some fungi, the presence or absence of free water on the surface of leaves, so-called leaf wetness, is key for infection and/or sporulation and is therefore an important parameter in disease epidemiology. A famous example is Phytophthora infestans, the causal agent of potato late blight, responsible for the Irish Potato Famine in the mid-19th century. The development of P. infestans depends on the presence of leaf wetness and the surrounding temperature.7, 8 In ideal circumstances, P. infestans can decimate a potato crop in less than 10 days. Control of late blight, as well as that of other pests and pathogens, is nowadays mostly done using crop protection products.9 There is, however, a strong push from policymakers to reduce this. Ea","cbCaihHjsFEYHiwA","https://ap.wps.com/l/cbCaihHjsFEYHiwA","pdf",4373393,1,11,"English","en",105,"# Abstract\n# Introduction\n## Motivation for THz applications and limitations\n## Leaf wetness and disease relevance in agriculture\n## Suitability of terahertz sensing and comparison with other technologies\n# Experimental approach and dataset description\n## Transmission setup and water-pattern measurements\n## Data organization by gravimetric water patterns","[{\"question\":\"What problem does the study address for THz spectroscopy applications?\",\"answer\":\"It addresses how to mature THz spectroscopy into practical applications by using effective signal processing and accelerating reliable parameter extraction with machine learning and physics guidance.\"},{\"question\":\"Why is leaf wetness important in the proposed agriculture application?\",\"answer\":\"Leaf wetness, i.e., the amount of free water on leaves, is a key parameter for infection and sporulation dynamics in diseases, enabling improved prediction and targeted control measures.\"},{\"question\":\"How is the THz dataset obtained in this work?\",\"answer\":\"The study experimentally acquires THz time-domain transmission signals of moist plant leaves across many distinct water (moisture) patterns.\"},{\"question\":\"Which machine learning methods are evaluated, and what ensures their relevance?\",\"answer\":\"Decision trees and convolutional neural networks are applied, using physics-motivated choices to improve how model features relate to the underlying light–matter interactions and to test generalizability under deviations from training data.\"}]","Physics-assisted machine learning for THz spectroscopy - sensing moisture on plant leaves | PDF",1785934374,28,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"physics-assisted-machine-learning-for-thz-spectroscopy-sensing-moisture-on-plant-leaves","",{"@graph":36,"@context":89},[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/physics-assisted-machine-learning-for-thz-spectroscopy-sensing-moisture-on-plant-leaves/126716/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address for THz spectroscopy applications?","Question",{"text":75,"@type":76},"It addresses how to mature THz spectroscopy into practical applications by using effective signal processing and accelerating reliable parameter extraction with machine learning and physics guidance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is leaf wetness important in the proposed agriculture application?",{"text":80,"@type":76},"Leaf wetness, i.e., the amount of free water on leaves, is a key parameter for infection and sporulation dynamics in diseases, enabling improved prediction and targeted control measures.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the THz dataset obtained in this work?",{"text":84,"@type":76},"The study experimentally acquires THz time-domain transmission signals of moist plant leaves across many distinct water (moisture) patterns.",{"name":86,"@type":73,"acceptedAnswer":87},"Which machine learning methods are evaluated, and what ensures their relevance?",{"text":88,"@type":76},"Decision trees and convolutional neural networks are applied, using physics-motivated choices to improve how model features relate to the underlying light–matter interactions and to test generalizability under deviations from training data.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]