[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82693-en":3,"doc-seo-82693-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},82693,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Signal from Space Detecting Schools and Towers to Bridge the Digital Divide","Reliable internet access is essential for modern education, yet millions of children in developing regions cannot connect because schools are not linked to networks. The Giga Initiative targets school connectivity by 2030, but large-scale mapping needs efficient, scalable ways to locate schools and assess nearby infrastructure. This work proposes a vision-only framework using high-resolution satellite imagery and transfer learning to detect schools and cellular towers, then infer connectivity via spatial and terrain-aware point-to-point line-of-sight analysis. Evaluated on Lesotho imagery, the method supports data-driven investment prioritization.","Signal from Space: Detecting Schools and Towers to Bridge the  \nDigital Divide  \nZakarya Elmimouni ∗ , Sandor Farkas †, Fares Fourati ∗ , Vladimir Daigele †, Walid Mathlouthi †, Mohamed-Slim  \nAlouini ∗  \narXiv :2607 .02724v 1 [ cs .CV] 2 Jul 2026  \nAbstract—Reliable internet access is essential for modern education, yet millions of school-aged children especially in developing regions remain offline due to unconnected schools. The Giga Initiative aims to connect every school to the internet, but doing so at scale requires efficient methods to map schools and assess surrounding connectivity infrastructure without relying on sparse or noisy third-party datasets. In this work, we propose a scalable, vision-only framework that uses high-resolution satellite imagery and transfer learning to address both tasks simultaneously. By adapting pre-trained object detection models to new geographical regions with minimal labeled data, we detect schools and cellular towers directly from space. We then analyze the spatial relationship between detected schools and nearby towers as a proxy for connectivity availability . This purely imagery-driven pipeline enables large-scale infrastructure mapping, reduces dependency on auxiliary data, and supports data-driven prioritization of connectivity investments in underserved areas. Our approach is demonstrated on real satellite imagery from Lesotho, showing strong performance across this region.  \nIndex Terms—School-Connectivity, School Detection, Cell Tower Detection.  \nI. INTRODUCTION  \nThe global learning crisis faces an urgent inflection point: nearly 2.2 billion people remain offline [1], with children in low-income countries disproportionately excluded from digital opportunity [2] . In Sub-Saharan Africa, the situation is particularly alarming: a study by UNICEF and the International Telecommunication Union (ITU) shows that 95% of schoolage children in West and Central Africa (194 million) and 88% in East and Southern Africa (191 million) lack internet access at home [3] . In Latin America and the Caribbean, 49% of children aged 3 to 17 remain unconnected. These stark regional disparities underscore the urgency of bridging the digital divide to guarantee inclusive and equitable education for all [3] .  \nIn response, UNICEF and the ITU launched the Giga Initiative, aiming to connect every school to the internet by 2030 [4] . Giga’s approach rests on three interdependent pillars: first, mapping the precise locations of schools; second, modeling the surrounding infrastructure including cellular towers and fiber routes that can support connectivity; and third, using these maps to plan and finance the deployment of internet services to unconnected schools. Giga’s early tool, Project Connect,  \n∗ King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia.  \n†International Telecommunication Union (ITU), Geneva, Switzerland. Emails: [zakarya.elmimouni@gmail.com](zakarya.elmimouni@gmail.com), {fares.fourati, slim.alouini}@kaust.  \n[edu.sa {sandor.farkas](edu.sa {sandor.farkas), vladimir.daigele, walid.mathlouthi}@itu.int Corresponding author: Zakarya Elmimouni  \nevolved into Giga Maps, which today shows more than 2.2 million schools across 140 countries [4] .  \nTo support such large-scale connectivity planning, the International Telecommunication Union (ITU), in partnership with Ericsson, has developed the Connectivity Planning Platform (CPP) a geographic information system-based tool designed to help decision-makers visualise, analyse, and address infrastructure gaps using multi-source geospatial data, population distribution, and terrain elevation models [5] . The CPP enables evidence-based assessments of potential point-to-point (P2P) links, making it particularly well-suited for evaluating whether a detected school can realistically be connected to a nearby cellular tower. In this work, we leverage the CPP’s P2P radio visibility analysis model as the core of our connectivity in","cbCaioyWBFCQdooR","https://ap.wps.com/l/cbCaioyWBFCQdooR","pdf",7890250,1,6,"English","en",105,"# Introduction\n## Background: the digital learning gap and Giga Initiative\n## Problem: limitations of third-party connectivity data\n## Proposed solution: vision-only school and tower detection\n## Connectivity inference: terrain-aware point-to-point assessment","[{\"question\":\"What core problem does the document address?\",\"answer\":\"Millions of school-aged children remain offline because many schools lack connected infrastructure, making large-scale planning difficult without reliable mapping data.\"},{\"question\":\"How does the proposed framework detect schools and towers?\",\"answer\":\"It uses high-resolution satellite imagery with transfer learning to fine-tune an object detection model for schools, then applies an oriented bounding box detector to locate cellular towers in the same region.\"},{\"question\":\"How is connectivity availability estimated from the detected objects?\",\"answer\":\"The method analyzes the spatial relationship between each detected school and its nearest tower using an ITU CPP point-to-point radio visibility model that incorporates terrain elevation to assess true line-of-sight.\"}]",1784182325,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"signal-from-space-detecting-schools-and-towers-to-bridge-the-digital-divide","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/signal-from-space-detecting-schools-and-towers-to-bridge-the-digital-divide/82693/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What core problem does the document address?","Question",{"text":74,"@type":75},"Millions of school-aged children remain offline because many schools lack connected infrastructure, making large-scale planning difficult without reliable mapping data.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed framework detect schools and towers?",{"text":79,"@type":75},"It uses high-resolution satellite imagery with transfer learning to fine-tune an object detection model for schools, then applies an oriented bounding box detector to locate cellular towers in the same region.",{"name":81,"@type":72,"acceptedAnswer":82},"How is connectivity availability estimated from the detected objects?",{"text":83,"@type":75},"The method analyzes the spatial relationship between each detected school and its nearest tower using an ITU CPP point-to-point radio visibility model that incorporates terrain elevation to assess true line-of-sight.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]